Hey Doc: I want to ask another question regarding deer, and this time I CAN sleep while waiting for an answer.
My questions relate to those little whistles that go on the front bumper. What do they actually do and do they work? Now that I have hit a deer, I am nervous about hitting another. Before I hit that one two weeks ago, I rarely ever saw them. Now I see an average of one every other day. Are they taunting me? You're the best, Doc! - Anonymous
Anon: I'm the best? I'll alert my wife. On to your question . . . There are hundreds of articles on the Internet that provide a substantial amount of evidence showing that deer whistles do not work. However, one of the better summaries is located here.
By the way, you're probably correct in guessing that the deer are taunting you. They know that you whacked one of their buddies and I'm sure they are intentionally trying to harass you. Well, OK, so maybe not. It might be that you're now paying more attention to the road and what's going on around you.
Degrees of Freedom - A New Definition
Doc: I have a research question. I just finished a research class and during the semester we had several discussions of the research term Degrees of Freedom. Although the professor tried many times to explain the concept, many of the students in the class, including me, always had questions, primarily because the Degrees of Freedom computation is different for each statistical method. The discussion always ended the same way when the professor would tell us that the Degrees of Freedom is "the number of values in the final calculation of a statistic that are free to vary." That's still confusing to me so I searched the Internet for more information.
On a few websites that that discuss your new 9th Edition of the research book you wrote with Joe Dominick, there are mentions that the it includes a new definition of Degrees of Freedom - the first new re-definition since the concept was developed in the early 1920s. Unfortunately, I don't have a copy of your book, so I would like to ask if you would include your new definition in your column. I would really appreciate it. Thanks in advance. - Anonymous
Anon: You don't have a copy of our book, eh? Well, OK, but before I include my new definition, I would like to provide a little background on why I developed a new definition for Degrees of Freedom.
I'm not sure if you know, but whenever most authors of academic textbooks prepare a new edition of a text, the publishing company contracts with several professors to provide a review of the text and make suggests for things to include in a new edition. In our case, we received seven very comprehensive reviews from professors from around the world who use our text in their research classes. One professor commented on the difficulty many students have in understanding Degrees of Freedom and suggested that we develop a new definition for our new 9th edition that became available in January 2011.
I thought the professor's suggestion was interesting because I have found the same student confusion with Degrees of Freedom while teaching on-and-off since 1976. The problem was that I never gave much thought to developing a new, and hopefully clearer, definition for a concept that has been around since the early 1920s. The reviewer's comments provided the encouragement I needed.
The new definition in the 9th edition is on pages 305-308 and includes a table I developed to demonstrate the effect Degrees of Freedom has on a data set. The complete discussion is a bit too much to include here in the column, so I'm only going to include an edited version of the complete explanation and new definition.
Degrees of Freedom
Most statistics historians would probably agree that the concept of degrees of freedom was first developed by British mathematician Karl Pearson (1857-1936) around 1900, but was refined, or more appropriately, corrected, by R. A. Fisher, in an article published in 1922. Both Pearson and Fisher shared a hatred of being wrong (and they also reportedly shared a hatred for each other), and in their quest for correctness, they realized that something was needed in statistical calculations to compensate for possible errors made in data collection, analysis, or interpretation. The fear of making an error is actually the foundation for the development of degrees of freedom.
The philosophy behind degrees of freedom is very simple—fear of being wrong. Since most research studies analyze data from a sample where the results are projected to the population, there is a need to make a slight adjustment to the sample to compensate for errors made in data collection and/or interpretation. This is because population parameters (the "real" data) are rarely, if ever, known to researchers. When calculating statistics for a sample, there is a need to have results that are somewhat conservative (corrected, adjusted) to compensate for any errors that may be present
The confusion surrounding degrees of freedom might be reduced if the concept had another name or definition. From our previous discussion, we can say that, in essence, the "key" to degrees of freedom is not that data are free to vary, but rather the concept relates to an adjustment made to data to provide a slightly more conservative estimate of the data to compensate for the possibility of errors in data collection, analysis, or interpretation. Therefore, our formally stated definition for degrees of freedom is:
An intentional and predetermined reduction in sample size to provide a conservative data adjustment
to compensate for research error.
There is the edited discussion. As you can see, the new definition highlights the fact that Degrees of Freedom is a reduction in sample size to compensate (somewhat) for research error. I hope that helps, but let me know if you have any other questions.
Note: I need to include that the definition for Degrees of Freedom has a 2011 copyright by Wadsworth Cengage Learning, which means that you're not supposed to use the information in any form without permission from the company.
Degrees Keyboard Key - How did you do that?
Hey Doc: I just read your answer to the question about Polarized sunglasses and noticed that you used the little symbol for degrees. How did you do that? This made me think of one more thing…where is the “cents” key on my keyboard? - Anonymous
Anon: To type the degrees symbol, such as 90°, you need to hold down your Alt key and type the number 0176 on your number pad (not the numbers above the letters on your keyboard). It only works with your number pad.
If you use Windows, all this information is available by going to Start, Programs, Accessories, System Tools, Character Map.
Your “cents” key is gone, but you can still type it with Alt 0162. Like this…¢.
In case you’re interested, here are a few other common symbols you can type with your Alt key: ™ (0153), © (0169), ® (0174), ¼ (0188), ½ (0189), ± (0177), ñ (0241).
(Delusional Parasitosis) Bugs or Something
Doc: One of the DJs at our
radio station always thinks he has bugs (or something) crawling on him and he is
constantly scratching his arms and legs (to the point of bleeding). Obviously,
something is wrong and I was wondering if you know anything about this? Thanks
in advance. - Anonymous
Anon: First, you'll notice that I edited your question quite a bit because you had some personal information about the person and I don't think he would enjoy having that information made public. I don't think I changed your question. Second, I need to say that I'm not a medical doctor, so don't interpret any of my comments as medical opinion.
However, I do know what you're talking about because my wife is a dermatologist and she encounters this situation quite often in her practice and has explained the condition to me several times. What the DJ at your radio station is experiencing is a condition known as Delusional Parasitosis, which is characterized by the person believing he/she is infested with some type of bug or insect. In reality, there are no bugs or insects, but the person believes it and may often actually cause bodily hard by scratching areas where the bugs/insects are supposedly located.
For more information, there are several articles in this search.
By the way, there probably isn't anything you or anyone else at the radio station can do for the person. Delusional Parasitosis is an extremely difficult condition for physicians to deal with, but your DJ friend should see a dermatologist, who may refer him to another specialist.
Deodorant - Aluminum and Cancer
Doctor: I read in a book that antiperspirants contain aluminum as an ingredient and that using deodorants with antiperspirant increases my risk of cancer. Sure enough, the first ingredient on my “Mitchum” was aluminum!
I tried switching to a deodorant without antiperspirant. Know what? I smelled none to pleasant way before I left work. So what's a brotha to do? Live longer and stink the station up, or get along well with others and risk death? - Anonymous
Anon: Your question is out of my area, so I asked my wife (a dermatologist). First, she said that there is no scientific evidence linking aluminum in deodorant to cancer. Secondly, she said that bacteria cause body odor and the way to eliminate odor is to eliminate or control the bacteria. So…one thing you can do is to use an antibacterial soap such as Lever 2000. Third, she said you could go to a doctor and ask for a prescription for an antibacterial deodorant that doesn’t have aluminum (but that seems extreme since there is no evidence linking aluminum and cancer).
There are many sources on the Internet explaining that aluminum (in deodorant or anything else) has not been linked to any type of cancer. Here is one good one: Snopes. All information suggests that you can go back to your Mitchum product. If you’re still hesitant, then I suggest that you visit a dermatologist.
Deodorant - Aluminum and Cancer – Follow-Up
Doc: In response to one of your questions, I had always heard that the aluminum in antiperspirant was thought to contribute to Alzheimer’s, not cancer. The aluminum in table salt (to keep it from clumping) is another source that was concerning people. Of course, this came from a high school science teacher, so who knows the validity of it all. - Jason
Jason: Sorry, but another urban legend and your science teacher was wrong. It’s amazing to me how such pseudoscience garbage continues to float around.
There are hundreds of legitimate sources on the Internet that debunk the correlation between Alzheimer’s and aluminum. If you’re interested, I set up a search for you…click here: More Pseudoscientific Crap.
By the way, you’ll also find similar articles on the Alzheimer’s Association website. Thanks for writing.
My question is, “How has the 1996 FCC deregulation of radio affected what music is played, the cost of commercials, and employment in the industry?” - Anonymous
Anon: Because I’m a former full-time college professor (only part-time now), the best I’ll do is provide a few Google searches for you. You need to do the work on your own. However, I’ll be happy to comment on the things you do find.
Check these out. Not every item is relevant, but you should have enough to get you started:
Good luck with your project.
Design a Radio Station (Project)
I have to do a project to “build” my own fake radio station. It's based in Nashville, TN. It's going to be an Active Rock station because there is no active rock station there. Do you have an info that you think could help, such as concert venues to advertise at, DJs to hire, etc.? Thanks a lot. - Anonymous
Anon: OK, so you wanna build a radio station in Nashville?
First, your GM will be in charge of 11 radio stations in the area, live in Ouagadougou, and run your station via email.
Second, your PD will be in charge of 16 radio stations in the area, live in Frankenstein, Missouri, and program your station via email.
Third, you won’t have any jocks. You’ll receive voice tracks from some strangers in Ding Dong, Texas.
Fourth, you’ll have 76 sales people to sell the 26 units per hour corporate says you have to run.
Finally, you won’t have the corporate headquarters located in Nashville. These folks, who are always willing to help you, will be located here.
Uh-oh. Duh. I just read your question again and you say that you’re designing a fake radio station. Forget all the stuff I just wrote.
I’m not exactly sure what you’re looking for, but you should be able to find almost anything on the Internet. For example, in reference to concert venues in Nashville, go to Google and type in Nashville concert venues. You’ll find a whole load of stuff.
Follow the same procedure with Nashville DJs, although some people may say that you would have better luck at the unemployment office.
Use that same procedure to search for things. First type Nashville and then follow that with whatever you’re interested in. Good luck with the project.
Developing as a PD
How can a person develop as a program director? I started by programming a small market 150+ station and my career goal is to advance to a bigger market. Also, will you give us the top 3 fallacies of research. We (the All Access readers) are learning and listening. Thank you for your time and your effort of sharing knowledge? – Anonymous
Anon: In most cases, the best way to advance to a larger market PD is to do a good job in a smaller market and establish connections and friendships at the same time. I'm sure you have heard the phrase "it's who you know." Well, get known. Try to participate in all types of radio-related activities (e.g. convention presentations) so that you can become "known." After you have established a good track record in the smaller market, let your connections know that you're ready to move on.
The top three fallacies of research? How about the top 24?
1. The data in research projects are "real" and contain no error.
2. Anyone can conduct a research study.
3. One statistical methodology is appropriate for all situations.
4. It's easy to write a good questionnaire.
5. Research is cheap.
6. It's easy to find 400 respondents for a telephone study.
7. Respondents in research studies care as much about radio as those who conduct and use the research.
8. The "accuracy" or research increases in direct relation to an increase in size (i.e., the larger the sample, the "better" the data.)
9. Research that uses high-tech "thingies" is better than research that doesn't.
10. All people who run research companies are researchers.
11. On-line (Internet) research will solve all research problems.
12. Research is the same regardless of who conducts it. The only difference is cost.
13. Arbitron methodology is correct only when your radio station ranks #1.
14. Results from two focus groups are good enough to make decisions about a radio station.
15. Sample sizes in large markets should be larger than sample sizes in small or medium markets.
16. Anyone can analyze perceptual study tables.
17. It's not important to know the sources of Internal Validity in research.
18. It's not important to follow the tenets (rules) of the scientific method in radio research.
19. Gut decisions are equal to (or better) than asking listeners.
20. If the data don't support a personal belief, opinion, or decision, there must be something wrong with the data.
21. Virgin (never participated before) respondents are needed for music tests.
22. It makes sense to design a screener to make it almost impossible to find respondents (e.g. 18-34 white females who are P1s, listen to the morning show at least 3 days each week, and also cume the competitor's morning show, and rate a music montage as 8, 9, or 10).
23. Complicated research methods are better than simple methods.
24. Someone who makes a comment using the word "we" does not necessarily represent everyone, but thanks for your vote of confidence.
If I thought about it, I probably could come up with a few more.
I hope this isn't too technical. In statistics, why are deviations scores squared? Why can't the scores just be added together? - Anonymous
Anon: Your question may be a bit too technical for someone who doesn't have a lot of experience with statistics, but it's important to you, so I'll address it. I apologize to readers who may not understand the question or the answer. I'll add a few descriptions of things to "ease the way" for those who don't have a statistics background.
As you know, a deviation score is simply the difference an original score is from the mean of the data set. Let's say that a data set (it could be music scores or personality ratings or any other type of measurement) has a mean of 10. And let's say that your score is 8. Your deviation score (your difference from the mean) is-2, or two units below the mean. Another person might have a score of 12, or +2 units above the mean.
Now, you can add all the deviation scores in the data set, but your sum is always zero because the deviation scores are computed by subtracting the mean from each individual score. The sum of deviation scores is always zero regardless of the data set.
However, the sum of "zero" isn't very useful for further analysis. In addition, dealing with negative numbers gets a bit goofy. So statisticians solve two problems simultaneously by squaring the deviation scores: negative numbers are eliminated, and there is no zero to deal with since the numbers are squared and summed. In statistics, this is cool, because squaring the deviation scores actually analyzes the absolute value of each score—for example, a score is two units from the mean and it doesn't matter whether it's above (+) or below (-) the mean. The sum of the squared deviation scores is then used to compute variance, standard deviation, and other statistical computations. (Do you understand? The sum of squared deviations is an indication of the absolute value difference of the individual scores from the mean of the data set.)
Squaring all of the individual score deviations does not change the meaning of the data because each score receives the same treatment (squaring). The process of transforming data in this manner (the same thing is done to all scores) is called monotonic transformation.
What does it stand for? - Anonymous
Anon: You’ll find the answer if you click here and click on the “Biography” link near the top of the page.
Dial Position and Arbitron
Doctor: Is there a relationship between a radio station's dial position and it's performance in Arbitron? - Anonymous
Anon: I may be wrong, but I'm guessing that you're new to the industry since this information has been around for a while. But that's fine because we all start from ground zero.
I have done this analysis dozens of times and have never found a correction between dial position and Arbitron performance. However, that doesn't mean it's the same in your market. Scientific information is self-correcting, so you may find something different. If you do, please let me know.
And here is how you can check your market (or any market).
Use a spreadsheet for the calculation. You'll be using the Pearson Product Moment Correlation. I'll use the formula for Excel, but I'm sure it's similar in the other spreadsheets.
First, don't combine AM and FM radio stations in one spreadsheet. That wouldn't be a legitimate analysis. Compute the correlation only for AM or only for FM.
Next . . . let's assume you have 15 radio stations in your market. In Column "A," enter the radio stations' frequencies in your market. In Column "B," enter the Arbitron shares from the demographic (12+, 18-34, etc.) and daypart you're interested in.
At the bottom of Column B, enter this formula for the correlation:
When you hit the "Enter" key, you'll see the Pearson Product Moment Correlation number, which can range from –1.00 to +1.00. If there is a relationship between dial position and Arbitron share, your number will be positive. However, in order to be meaningful, you'll need to have a positive number of .75 or higher.
A negative correlation indicates an inverse relationship between the two variables—as dial position goes up, Arbitron performance goes down. However, as with the positive number, you'll need a negative correlation of -.75 or greater to be meaningful.
If you do the correlation, please send me the results. I gots ta know if anything has changed.
Dial Position and Arbitron - Response
Doc: I followed your instructions for doing a correlation between the 15 FM radio stations in my market and their Arbitron 12+ shares. The correlation was 25 percent. I know you said the number needs to be .75 or higher to be considered significant, but what does the 25 percent number that I got really mean? Thanks. - Rick
Rick: I'm glad to hear that you computed the correlation. Good for you. However, I need to correct you on one thing before I get to your question.
You said that the correlation you computed was 25 percent. The Pearson Product Moment Correlation (usually just called "correlation" and abbreviated with a lower case "r") is not a percentage or a proportion—your .25 correlation does not mean it is one-quarter of anything. A correlation number only indicates a correlational relationship between two variables, not a causal relationship between them. In other words, if two variables are highly correlated, it doesn't mean that one "causes" the other. In a discussion, you would say that you computed a correlation of .25 ("point two five" or "point twenty-five").
Now, you asked what your r of .25 really means. First, remember that a correlation of zero means absolutely no relationship between the two variables. Your .25 is just slightly above zero, which means that there is only a very low correlation between the dial position of the 15 FM radio stations in your market and their 12+ performance in Arbitron—an FM radio station in your market at the left side of the dial has the same likelihood of Arbitron success as an FM radio station at the right side of the dial, or any other place on the FM dial.
If you're interested in statistics stuff, here are a few more things for you . . .
There are a few other things you can do with correlations. One is to convert your correlation to a Z-score so you can do other things with the number, such as compare it to other markets. A second thing is to test the statistical significance of your correlation. Both of these calculations can be done easily on this neat website.
Here is what you can do when you go to that site:
z-score: Go down the page to the section titled, "Fisher r-to-Z Transformation." When you enter your data (.25 and 15 for "N"), you'll see that your .25 correlation converts to a z-score of .2554 (just a coincidence that the numbers are virtually the same). A z-score of "0" is the mean (average), so it's clear that your correlation lies just above the mean—not great.
Statistical significance: Go down the page to the section titled, "r to P Calculator." When you enter your data, you'll see that your number is significant at the .3668 probability level. What does that mean? In brief, it means that you can only be about 63.32% sure that your results are significant (1.00 - .3668). Another way to interpret this is to say that if you replicated (repeated) your study in the future, there is a 36% chance that your results are due to error (or chance). This isn't good. For example, in media research, we usually test at a probability level of .05, which means that we're 95% confident in the results of the test. However, in medical research, studies are usually tested at a probability of .001 (the results in 1 out of 1,000 studies are due to chance or error), .0001 (1 out of 10,000), and even .00001 (1 out of 100,000)
Doc: The question about the origin of vegetable names reminded me of something about a word pronunciation because it comes up once in a while in our news copy that I read. The word is diabetes. When I was younger, the word was pronounced DIE-a-BEET-us. Somewhere in the past several years, the pronunciation became DIE-a-BEET-EZE. What's with the "EZE" part at the end? Which is the correct pronunciation? (I hope my typing of the pronunciations is correct.) - Anonymous
Anon: Yes, I think everyone will understand how you typed each of the pronunciations.
I also have wondered about this because diabetes was always pronounced, as you wrote it, DIE-a-BEET-us, but I can't tell you when the pronunciation changed. However, according to the Merriam-Webster online dictionary, both of the pronunciations are correct, although the "EZE" option is listed first.
By the way, we aren't the only people who have wondered about the pronunciation of the word. There are several articles on the Internet, some of which are very passionate about the correct pronunciation. For example, you might find this discussion interesting.
Didn't Answer General Manager Question
I sent you a question about my GM (AC radio station to remind you) a few weeks ago and you never answered it or even posted it in the column. How come? I thought you answered all questions. When are you going to answer my question? - Ray
Ray: My, my, calm down there, Ray. Sounds like your shorts are frosted. Now, I may be dumb, but I’m not stupid. I didn’t answer your question or post it on the column because your “question” was not a question, but rather a personal attack on your GM couched as a question.
My purpose for the column is to try to answer legitimate questions primarily about radio, but also about any topic. My purpose for the column is not to provide a soapbox for people to vent their frustrations. If you have a problem with your GM, then talk to him about it. I’m not going to post your note because it’s filled with invectives, insinuations, innuendoes, and unsubstantiated claims.
If you’re new to the column, you may not know that I do answer private questions. That is, I don’t post my response on the column, but send it via email. However, if you would have asked for a private answer, I would have told you the same thing: Talk to your GM.
So there. Your question will not appear on the column. Defrost your shorts.
Didn't Answer Question (Another Time)
Doc: I sent you a question about [person's name deleted by Wimmer] about a week ago and you didn't answer it yet. How come? If you don't post it, I'm going to contact Joel Denver and complain. - Anonymous
Anon: The reason I didn't answer your question is due to the fact that your question wasn't a question. It was merely a vindictive diatribe aimed at a well-known person in radio and I don't think posting your comments would serve any useful purpose.
I'll answer just about any question, but I won't address questions/comments/criticisms of individuals or groups. You'll have to find another place to vent your frustrations.
If you want to write to Joel Denver at AllAccess.com, please do so . . . just click here. I'm sure he will be thrilled to hear from you.
Diesel Engine Noise
Doc: I have always wondered why diesel engines make so much noise. They are very annoying when they pull up next to me at a stoplight. Do you know why the engines are so obnoxious? By the way, it seems to me that Ford diesels are the loudest. - Anonymous
Anon: I know something about engines, but I decided to get help from one of my good friends, Keith Duner, who is a top executive with Allison Transmissions. This is what he said:
Gas engines run at a relatively low compression ratio (i.e. somewhere between 7-12 to 1 volume reduction (as the piston travels up the cylinder bore to the spark/fuel source) and use an ignition source (spark plug). Diesels, however, run a significantly higher compression ratio (up to 24-28 to 1) and typically use the elevated temperature (caused by the higher compression ratio) as the means to ignite the air/fuel mixture (some diesels use glow plugs to start in cold weather.) This is also why diesels typically produce more torque (not necessarily horsepower) than a comparable gas engine.
The resultant bang (the exploding air/fuel mixture driving the piston down) is typically louder in the diesel because of the higher compression ratio. While I don’t know if or why Ford diesels are louder, I do know that some Original Equipment Manufactures will “tune” the vehicles sound output (via manipulation of sound attenuation material around the engine) to foster the “Big Diesel Rig image” as a sales tool. It’s a guy thing I guess.
Digging a Hole to China
I saw a short story on ABC network news about digging a hole to China. The story showed that if you dig a hole straight down anywhere in the United States, you would "come out" in the Indian Ocean. I thought that was interesting and wondered if there is a way to figure out where you would "come out" if you dug at various places around the Earth. - Anonymous
Anon: Interesting question, and there is a website to do just that. It's based on information from Google Maps—click here and follow the directions on the screen. Be patient with the website. It loads very slowly, which is probably due to the number of people trying to access the URL.
Digital Copyright Act
If you could please give me a brief overview of what is stated in the DMCA. And if you could please tell me where I can find the whole document in its entirety online. Thank you for your help. - Scotty Jay
Scotty Jay: Your brief summary: the Digital Millennium Copyright Act that President Clinton signed into law on October 28, 1998, prohibits "any technology, product, service, device, component, or part thereof, that...is primarily designed or produced for the purpose of circumventing protection afforded by a technological measure that effectively protects a right of a copyright owner."
Several sites for you to visit for more information:
For an online copy of the Act, click here: http://www.educause.edu/issues/dmca.html
Dihydrogen Monoxide Petition
Doc: Would you be willing to
sign my petition banning Dihydrogen Monoxide? I think it's something we all
should do. - Jay
Jay: Oh, please. Don't make me come out there. No, I wouldn't sign your petition because even someone like me who has only a rudimentary knowledge of chemistry knows that Dihydrogen Monoxide is another way to say, "water." I also think that anyone with a few brain cells would search the Internet and find that your petition idea isn't new as evidenced by these articles.
However, I think the original idea by Nathan Zohner in 1997 (when he was 14), was great. As you probably know, he, gathered petitions to ban DHMO for his science project, titled "How Gullible Are We?"
Doc: I occasionally see bikers
with patches that say. "DILLIGAF." Do you know what that means? - Anonymous
Anon: I'll give you the first seven words. I think you should be able to figure out the last word. The acronym stands for: Does It Look Like I Give A F***.
Click Here for Additional D Questions
All Content © 2015 - Wimmer Research All Rights Reserved